Upload folder using huggingface_hub

config.json

@@ -0,0 +1,92 @@
+{
+  "_name_or_path": "Omarrran/english_speecht5_finetuned",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SpeechT5ForTextToSpeech"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.1,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.1,
+  "encoder_layers": 12,
+  "encoder_max_relative_position": 160,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "guided_attention_loss_num_heads": 2,
+  "guided_attention_loss_scale": 10.0,
+  "guided_attention_loss_sigma": 0.4,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 1876,
+  "max_speech_positions": 1876,
+  "max_text_positions": 600,
+  "model_type": "speecht5",
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_mel_bins": 80,
+  "pad_token_id": 1,
+  "positional_dropout": 0.1,
+  "reduction_factor": 2,
+  "scale_embedding": false,
+  "speaker_embedding_dim": 512,
+  "speech_decoder_postnet_dropout": 0.5,
+  "speech_decoder_postnet_kernel": 5,
+  "speech_decoder_postnet_layers": 5,
+  "speech_decoder_postnet_units": 256,
+  "speech_decoder_prenet_dropout": 0.5,
+  "speech_decoder_prenet_layers": 2,
+  "speech_decoder_prenet_units": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "use_guided_attention_loss": true,
+  "vocab_size": 81
+}

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_ceptral_normalize": true,
+  "do_normalize": false,
+  "feature_extractor_type": "Speech2TextFeatureExtractor",
+  "feature_size": 1,
+  "fmax": 7600,
+  "fmin": 80,
+  "frame_signal_scale": 1.0,
+  "hop_length": 16,
+  "mel_floor": 1e-10,
+  "normalize_means": true,
+  "normalize_vars": true,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "SpeechT5Processor",
+  "reduction_factor": 2,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_function": "hann_window",
+  "win_length": 64
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd9bf63c0fef00f5b4c0dfd6141830a72635c0d4715fdcb14e4646c1ce3fa8d
+size 186775626

quantization.log

@@ -0,0 +1,27 @@
+2024-10-22 09:40:39,200 - SpeechQuantizer - INFO - Loading model components on cuda...
+2024-10-22 09:40:39,307 - SpeechQuantizer - INFO - Attempting to load tokenizer from Omarrran/english_speecht5_finetuned
+2024-10-22 09:40:39,416 - SpeechQuantizer - WARNING - Original tokenizer loading failed: expected str, bytes or os.PathLike object, not NoneType
+2024-10-22 09:40:39,428 - SpeechQuantizer - INFO - Attempting to load tokenizer from fallback model facebook/s2t-small-librispeech-asr
+2024-10-22 09:40:39,553 - SpeechQuantizer - INFO - Successfully loaded tokenizer from facebook/s2t-small-librispeech-asr
+2024-10-22 09:40:40,372 - SpeechQuantizer - INFO - Model components loaded successfully
+2024-10-22 09:40:40,386 - SpeechQuantizer - INFO - Memory usage: RSS=3731.4MB
+2024-10-22 09:40:40,395 - SpeechQuantizer - INFO - GPU memory: 2342.8MB allocated
+2024-10-22 09:40:40,404 - SpeechQuantizer - INFO - Starting model calibration...
+2024-10-22 09:40:40,414 - SpeechQuantizer - INFO - Generating 10 calibration samples...
+2024-10-22 09:40:45,565 - SpeechQuantizer - WARNING - Sample generation failed: chirp() takes 0 positional arguments but 4 were given
+2024-10-22 09:40:45,592 - SpeechQuantizer - WARNING - Sample generation failed: chirp() takes 0 positional arguments but 4 were given
+2024-10-22 09:40:45,609 - SpeechQuantizer - WARNING - Sample generation failed: chirp() takes 0 positional arguments but 4 were given
+2024-10-22 09:40:45,619 - SpeechQuantizer - WARNING - Sample generation failed: chirp() takes 0 positional arguments but 4 were given
+2024-10-22 09:40:45,651 - SpeechQuantizer - INFO - Successfully generated 6 calibration samples
+2024-10-22 09:40:45,749 - SpeechQuantizer - WARNING - Calibration sample failed: SpeechT5ForSpeechToText.forward() got an unexpected keyword argument 'input_features'
+2024-10-22 09:40:45,766 - SpeechQuantizer - WARNING - Calibration sample failed: SpeechT5ForSpeechToText.forward() got an unexpected keyword argument 'input_features'
+2024-10-22 09:40:45,785 - SpeechQuantizer - WARNING - Calibration sample failed: SpeechT5ForSpeechToText.forward() got an unexpected keyword argument 'input_features'
+2024-10-22 09:40:45,801 - SpeechQuantizer - WARNING - Calibration sample failed: SpeechT5ForSpeechToText.forward() got an unexpected keyword argument 'input_features'
+2024-10-22 09:40:45,814 - SpeechQuantizer - WARNING - Calibration sample failed: SpeechT5ForSpeechToText.forward() got an unexpected keyword argument 'input_features'
+2024-10-22 09:40:45,824 - SpeechQuantizer - WARNING - Calibration sample failed: SpeechT5ForSpeechToText.forward() got an unexpected keyword argument 'input_features'
+2024-10-22 09:40:45,832 - SpeechQuantizer - INFO - Calibration completed: 0/6 samples successful (0.0%)
+2024-10-22 09:40:45,840 - SpeechQuantizer - WARNING - No successful calibrations. Proceeding with caution.
+2024-10-22 09:40:45,847 - SpeechQuantizer - INFO - Starting quantization process...
+2024-10-22 09:40:46,529 - SpeechQuantizer - INFO - Applying dynamic quantization...
+2024-10-22 09:40:48,931 - SpeechQuantizer - INFO - Quantization completed successfully
+2024-10-22 09:40:48,950 - SpeechQuantizer - INFO - Saving and pushing model...

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052a168787a9160b4b2ba54e4995e9600298812c34191ca3f70cea51cd4f5c1e
+size 416684

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "do_upper_case": false,
+  "eos_token": "</s>",
+  "lang_codes": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tgt_lang": null,
+  "tokenizer_class": "Speech2TextTokenizer",
+  "unk_token": "<unk>"
+}